我在假期为了完成写综述的任务,深度体验和对比了多款学术论文Agent。其中有几款给我留下的印象很深,效果也是相当不错。下面我用“AI治理”为主题让这几款Agent进行PK!
Pasa-agent
首先登场的是:PaSa-agent.Pasa是字节跳动研究团队推出的基于强化学习的学术论文检索智能体,这是关于它的详细介绍:
功能特点
- 自主调用搜索工具:能自动调用搜索引擎,根据用户输入的学术问题生成多样化的搜索关键词,并执行多次搜索,确保全面覆盖相关文献。
- 阅读和分析论文内容:通过Crawler和Selector两个核心组件,高效地收集和筛选相关论文,从海量文献中筛选出与用户查询最相关的参考文献,确保检索结果的精确性。
- 支持复杂学术查询:专为处理复杂的学术问题设计,能够理解并处理细粒度的学术查询,例如涉及特定算法或研究方法的问题。
技术原理
- 核心组件:包括Crawler和Selector两个主要的LLM智能体。Crawler负责通过搜索引擎收集与用户查询相关的学术论文。Selector则负责精读每一篇论文,评估其是否符合用户需求。
- 强化学习优化:使用强化学习(RL)和近端策略优化(PPO)算法进行训练,通过合成数据集AutoScholarQuery和真实世界查询基准RealScholarQuery来提升搜索效率和准确性。
性能表现
- 在Recall@20和Recall@50指标上,PaSa比Google Scholar分别提升了37.78%和39.90%。
- 查全率比Google+GPT-4组合高出33.8%,性能超越搜索增强版ChatGPT。
- 与基于Prompt Engineering实现的PaSa - GPT-4o相比,经过强化学习训练的PaSa-7b在召回率上提升了30.36%,准确率上提升了4.25%。
应用优势
- 节省时间:能够在两分钟内完成一次详尽的学术调研,显著提升了文献检索的速度,让研究者把更多精力放在分析和撰写上。
- 精准全面:模仿人类研究者的行为,深入理解研究需求,不仅能找到直接相关的论文,还能通过引用关系挖掘更多重要参考文献,提供全面且准确的搜索结果。
开源与使用
检索效果
当我以The current development status of AI governance
为检索主题时得到了如下相关的论文集合。点开还可以直接查看论文的摘要、作者、发布时间等关键信息。进一步点开则可以直接预览pdf啦!
我们点开其中几篇论文查看与我们想要的东西是否契合,还阔以哈。
The organizational use of artificial intelligence (AI) has rapidly spread across various sectors. Alongside the awareness of the benefits brought by AI, there is a growing consensus on the necessity of tackling the risks and potential harms, such as bias and discrimination, brought about by advanced AI technologies. A multitude of AI ethics principles have been proposed to tackle these risks, but the outlines of organizational processes and practices for ensuring socially responsible AI development are in a nascent state. To address the paucity of comprehensive governance models, we present an AI governance framework, the hourglass model of organizational AI governance, which targets organizations that develop and use AI systems. The framework is designed to help organizations deploying AI systems translate ethical AI principles into practice and align their AI systems and processes with the forthcoming European AI Act. The hourglass framework includes governance requirements at the environmental, organizational, and AI system levels. At the AI system level, we connect governance requirements to AI system life cycles to ensure governance throughout the system’s life span. The governance model highlights the systemic nature of AI governance and opens new research avenues into its practical implementation, the mechanisms that connect different AI governance layers, and the dynamics between the AI governance actors. The model al